PREVIEW. This is how it will look in an inbox; it was not sent to you. Each real email carries its own unsubscribe link and Keryn's postal address.

Keryn Headlines

Daily, Friday 17 July 2026 · Retrospective · Covers 16 July 2026 00:00 to 17 July 2026 00:00 UTC

Read on the web

Top developments

CISA orders feds to patch actively exploited Oracle flaw by Saturday

BleepingComputer · Advisory · Remediation

Unpacking the AsyncAPI npm supply chain compromise and import-time payload delivery

Microsoft · Incident · SCA

CVE-2026-39808: Fortinet FortiSandbox OS Command Injection Vulnerability added to CISA's Known Exploited Vulnerabilities catalog

CISA · Advisory

SCA

Setup Complete, Now You Are Compromised: Weaponizing Setup Instructions Against AI Coding Agents

arXiv · Research · Agentic SDLC, SCA

The Distributed Open-Source Vulnerability Ecosystem

arXiv · Research · Remediation, SCA

DAST

Beyond Success Rate: Cost-Aware Evaluation of Offensive and Defensive Security Agents

arXiv · Research · DAST

AI Can Find Bugs, But Human Knowledge Still Proves Them

The Hacker News · Analysis · DAST

Agentic SDLC

Bad Memory: Evaluating Prompt Injection Risks from Memory in Agentic Systems

arXiv · Research · Agentic SDLC, AI Security

Democratizing Agent Deployment Safety: A Structural Monitoring Approach

arXiv · Research · Agentic SDLC, Trust

New Agent Data Injection Attack Can Make AI Agents Misclick or Run Attacker Commands

The Hacker News · Analysis · Agentic SDLC, AI Security

Trust

SCITUS: A Multi-Jurisdictional Framework for Adapting NIST AI RMF to the Canadian Regulatory Context

arXiv · Research · Trust

StructureClaw: Traceable LLM Agents and an Executable Benchmark for Structural Engineering Workflows

arXiv · Research · Trust

Global Index on Responsible AI 2026 : Conceptual Framework and Methodology

arXiv · Research · Trust

Models

When Words Are Safe But Actions Kill: Probing Physical Jailbreak Beyond Textual Jailbreak in Hidden-State Risk Space

arXiv · Research · Models

AI Security

FlowGuard: From Signals to Evidence for MCP Security Detection

arXiv · Research · AI Security

From Indirect Prompt Injection to DNS Exfiltration in macOS Terminal

Embrace The Red · Analysis · AI Security

Context Contamination in LLM Analysis of Network Security Logs: Poison with Passive Prompt Injection and Mitigation Evaluation

arXiv · Research · AI Security

Advisories in this window

  • 23 npm advisories · 22 critical · 1 high
  • 11 Go advisories · 1 critical · 2 high · 8 moderate
  • 5 PyPI advisories · 2 critical · 3 high
  • 4 Maven advisories · 4 high
  • 3 Packagist advisories · 1 critical · 2 high
  • 3 crates.io advisories · 1 moderate · 2 low

All advisories

Titles, links and short excerpts only; every item links to its source. Selection is automatic; the editor's note is AI-drafted and checked as described. Preview: the unsubscribe link and Keryn's postal address are added to each email when it is sent.